Using Machine Learning to Predict Multiphase Flow through Complex Fractures
Multiphase flow properties of fractures are important in engineering applications such as hydraulic fracturing, evaluating the sealing capacity of caprocks, and the productivity of hydrocarbon-bearing tight rocks. Due to the computational requirements of high fidelity simulations, investigations of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/23/8871 |
| _version_ | 1797463334466879488 |
|---|---|
| author | Allen K. Ting Javier E. Santos Eric Guiltinan |
| author_facet | Allen K. Ting Javier E. Santos Eric Guiltinan |
| author_sort | Allen K. Ting |
| collection | DOAJ |
| description | Multiphase flow properties of fractures are important in engineering applications such as hydraulic fracturing, evaluating the sealing capacity of caprocks, and the productivity of hydrocarbon-bearing tight rocks. Due to the computational requirements of high fidelity simulations, investigations of flow and transport through fractures typically rely on simplified assumptions applied to large fracture networks. These simplifications ignore the effect of pore-scale capillary phenomena and 3D realistic fracture morphology (for instance, tortuosity, contact points, and crevasses) that lead to macro-scale effective transport properties. The effect of these properties can be studied through lattice Boltzmann simulations, but they require high performance computing clusters and are generally limited in their domain size. In this work, we develop a technique to represent 3D fracture geometries and fluid distributions in 2D without losing any information. Using this innovative approach, we present a specialized machine learning model which only requires a few simulations for training but still accurately predicts fluid flow through 3D fractures. We demonstrate our technique using simulations of a water filled fracture being displaced by supercritical CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula>. By generating highly efficient simulations of micro-scale multiphase flow in fractures, we hope to investigate a wide range of fracture types and generalize our method to be incorporated into larger discrete fracture network simulations. |
| first_indexed | 2024-03-09T17:49:10Z |
| format | Article |
| id | doaj.art-2f50eb25a6cb46acbbc6db0f9ae0e030 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T17:49:10Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-2f50eb25a6cb46acbbc6db0f9ae0e0302023-11-24T10:51:38ZengMDPI AGEnergies1996-10732022-11-011523887110.3390/en15238871Using Machine Learning to Predict Multiphase Flow through Complex FracturesAllen K. Ting0Javier E. Santos1Eric Guiltinan2Computer Science Department, The University of Texas at Austin, Austin, TX 78712, USAEarth and Environmental Science Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USAEarth and Environmental Science Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USAMultiphase flow properties of fractures are important in engineering applications such as hydraulic fracturing, evaluating the sealing capacity of caprocks, and the productivity of hydrocarbon-bearing tight rocks. Due to the computational requirements of high fidelity simulations, investigations of flow and transport through fractures typically rely on simplified assumptions applied to large fracture networks. These simplifications ignore the effect of pore-scale capillary phenomena and 3D realistic fracture morphology (for instance, tortuosity, contact points, and crevasses) that lead to macro-scale effective transport properties. The effect of these properties can be studied through lattice Boltzmann simulations, but they require high performance computing clusters and are generally limited in their domain size. In this work, we develop a technique to represent 3D fracture geometries and fluid distributions in 2D without losing any information. Using this innovative approach, we present a specialized machine learning model which only requires a few simulations for training but still accurately predicts fluid flow through 3D fractures. We demonstrate our technique using simulations of a water filled fracture being displaced by supercritical CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula>. By generating highly efficient simulations of micro-scale multiphase flow in fractures, we hope to investigate a wide range of fracture types and generalize our method to be incorporated into larger discrete fracture network simulations.https://www.mdpi.com/1996-1073/15/23/8871machine learningmultiphase flowunsteady-statetime-dependencyhydraulic fractureslattice-Boltzmann |
| spellingShingle | Allen K. Ting Javier E. Santos Eric Guiltinan Using Machine Learning to Predict Multiphase Flow through Complex Fractures Energies machine learning multiphase flow unsteady-state time-dependency hydraulic fractures lattice-Boltzmann |
| title | Using Machine Learning to Predict Multiphase Flow through Complex Fractures |
| title_full | Using Machine Learning to Predict Multiphase Flow through Complex Fractures |
| title_fullStr | Using Machine Learning to Predict Multiphase Flow through Complex Fractures |
| title_full_unstemmed | Using Machine Learning to Predict Multiphase Flow through Complex Fractures |
| title_short | Using Machine Learning to Predict Multiphase Flow through Complex Fractures |
| title_sort | using machine learning to predict multiphase flow through complex fractures |
| topic | machine learning multiphase flow unsteady-state time-dependency hydraulic fractures lattice-Boltzmann |
| url | https://www.mdpi.com/1996-1073/15/23/8871 |
| work_keys_str_mv | AT allenkting usingmachinelearningtopredictmultiphaseflowthroughcomplexfractures AT javieresantos usingmachinelearningtopredictmultiphaseflowthroughcomplexfractures AT ericguiltinan usingmachinelearningtopredictmultiphaseflowthroughcomplexfractures |